The MultiText system retrieves passages, rather than entire documents, that are likely to be
relevant to a particular topic. For all runs, we used the reciprocal of the length of each …

The MultiText information retrieval system finds arbitrary passages of text, as opposed to
complete documents, that are likely to be relevant to a particular topic. Passage retrieval …

This paper describes an approach to information retrieval based on a syntactic analysis of
the document texts and user queries, and from that analysis, the construction of tree …

The HARD track of TREC 2004 aims to improve the accuracy of information retrieval through
the use of three techniques:(1) query metadata that better describes the information need,(2) …

TREC-8 represents the fifth year that the MultiText project has participated in TREC [2, 1, 4,
5]. The MultiText project develops and prototypes scalable technologies for parallel …

For the TREC 2004 Novelty track, UMass participated in all four tasks. Although finding
relevant sentences was harder this year than last, we continue to show marked …

The MultiText System implements a variety of retrieval methods, three of which were used in
our TREC 2003 experiments: 1) Shortest Substring Ranking (SSR), a ranked retrieval …

To address the TREC-4 topics, we used a precise query language that yields and combines
arbitrary intervals of text rather than pre-defined units like words and documents. Each …

The novelty track was first introduced in TREC 2002. Given a TREC topic and an ordered list
of documents, systems must find the relevant and novel sentences that should be returned to …

Queries for TREC-5 were formulated in the GCL query language using an interactive system
that showed short passages containing relevant terms. Solutions to the queries were ranked …